REVIEW 5 cited by
Deep Reinforcement Learning with Spiking Q-learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Deep Reinforcement Learning with Spiking Q-learning
read the original abstract
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former needs to tune numerous hyper-parameters for each scenario, and the latter limits the application of different types of RL algorithm and ignores the large energy consumption in training. To develop a robust spike-based RL method, we draw inspiration from non-spiking interneurons found in insects and propose the deep spiking Q-network (DSQN), using the membrane voltage of non-spiking neurons as the representation of Q-value, which can directly learn robust policies from high-dimensional sensory inputs using end-to-end RL. Experiments conducted on 17 Atari games demonstrate the DSQN is effective and even outperforms the ANN-based deep Q-network (DQN) in most games. Moreover, the experiments show superior learning stability and robustness to adversarial attacks of DSQN.
Forward citations
Cited by 5 Pith papers
-
NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework
A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.
-
Error Amplification Limits ANN-to-SNN Conversion in Continuous Control
Temporally correlated action errors, amplified by closed-loop dynamics, explain ANN-to-SNN conversion failures in continuous control, and cross-step residual potential initialization mitigates them.
-
Q-SpiRL: Quantum Spiking Reinforcement Learning for Adaptive Robot Navigation
QSNN agent in Q-SpiRL framework achieves up to 99% success rate with efficient paths in 20x20 to 40x40 grid worlds with static and dynamic obstacles, outperforming tabular Q-learning, MLP, SNN, and QMLP baselines unde...
-
Q-SpiRL: Quantum Spiking Reinforcement Learning for Adaptive Robot Navigation
A quantum-enhanced spiking Q-network is reported to outperform classical, spiking, and quantum-dense baselines in small grid-world navigation, with gains that are small relative to the reported error bars.
-
Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents
SwitchMT uses adaptive task-switching in deep spiking Q-networks with active dendrites to reduce task interference in multi-task RL, achieving competitive Atari scores without added network complexity.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.